GaZmagik/iso-24495 / skills/iso-24495-4
iso-24495-4
VerifiedProvisional task skill for organisational plain language implementation (based on ISO/CD 24495-4, committee draft). Activates for plain language gap analysis, policy drafting, review workflow design, and organisational readiness for the future published standard. Does not activate for ordinary writing, rewriting, or reviewing of individual documents.
tests/fixtures/corpus/average-heavy.md
View on GitHub# Sample With A High Average But No Single Offender
Every single sentence in this fixture document has been written quite deliberately to sit somewhere in the low twenties for its own word count. Not one of them ever crosses the thirty word cap, and so the per sentence rule can find nothing at all to report. The trouble in this prose only becomes visible when the engine steps back and considers the document as one whole connected piece of writing. A reader here faces sentence after sentence of this same sustained moderate length, with no shorter ones mixed in for relief.
The public plain language standards ask writers to keep the average sentence length across a whole document between fifteen and twenty words. This fixture pushes its own running average above that stated ceiling while still keeping every individual sentence inside the thirty cap. That precise combination is exactly the sustained failure mode which the old maximum only rule could never see or ever report. Any tool that only ever checks single sentences would wave this entire document straight through without one single comment, which is wrong.
The average rule needs to see a reasonable number of sentences before it can judge any document fairly and without excessive noise. Ten counted sentences is the minimum sample size this engine accepts before it will even compute the running average at all. This third paragraph exists mostly to carry the whole fixture safely past that minimum with more sentences of matching sustained length. Its final sentence now closes the fixture while it still holds the same deliberate twenty something word rhythm as all the rest.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |